Predicting Human Protein--Protein Interaction Sites by Integrating ESM-2 Sequence Embeddings and a Gated Graph Neural Network

Predicting Human Protein--Protein Interaction Sites by Integrating ESM-2 Sequence Embeddings and a Gated Graph Neural Network | Authorea try { document.documentElement.classList.add('js'); } catch (e) { } var _gaq = _gaq || []; _gaq.push(['_setAccount', 'G-8VDV14Y67G']); _gaq.push(['_trackPageview']); (function() { var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true; ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js'; var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s); })(); Skip to main content Preprints Collections Wiley Open Research IET Open Research Ecological Society of Japan All Collections About About Authorea FAQs Contact Us Quick Search anywhere Search for preprint articles, keywords, etc. Search Search ADVANCED SEARCH SCROLL This is a preprint and has not been peer reviewed. Data may be preliminary. 18 November 2025 V1 Latest version Share on Predicting Human Protein--Protein Interaction Sites by Integrating ESM-2 Sequence Embeddings and a Gated Graph Neural Network Authors : Merry K. P 0009-0003-2963-842X [email protected] and Angelina Geetha Authors Info & Affiliations https://doi.org/10.22541/au.176342634.43051222/v1 372 views 147 downloads Contents Abstract Supplementary Material Information & Authors Metrics & Citations View Options References Figures Tables Media Share Abstract Precision prediction of protein-protein interaction (PPI) sites is essential to the elucidation of cellular processes as well as drug design. Conventional approaches use hand-engineered properties and do not work well with the Protein living sequences. The new framework ESM-GNN, suggested as a paradigm, consisting of embedding ESM-2 protein language models into a gated graph neural network to predict the human PPI sites. This manual method uses rich contextual representations received by ESM-2 to learn evolutionary patterns and integrates them with graph-constrained learning to learn about spatial interactions between amino acids. On benchmark datasets, we find experimental results that ESM-GNN outperforms the other existing methods to perform as a state-of-the-art with 0.892 AUC and F 1 -score of 0.847 . The combination of pretrained protein embeddings with graph neural networks yields an efficient method of PPI site prediction which is a new paradigm of computational analysis of proteins. Supplementary Material File (sci_paper_3_final (4).pdf) Download 1013.91 KB Information & Authors Information Version history V1 Version 1 18 November 2025 Copyright This work is licensed under a Non Exclusive No Reuse License. Keywords deep learning esm-2 embeddings graph neural networks protein-protein interactions structural bioinformatics Authors Affiliations Merry K. P 0009-0003-2963-842X [email protected] Hindustan Institute of Technology and Science View all articles by this author Angelina Geetha Hindustan Institute of Technology and Science View all articles by this author Metrics & Citations Metrics Article Usage 372 views 147 downloads .FvxKWukQNSOunydq8rnd { width: 100px; } Citations Download citation Merry K. P, Angelina Geetha. Predicting Human Protein--Protein Interaction Sites by Integrating ESM-2 Sequence Embeddings and a Gated Graph Neural Network. Authorea . 18 November 2025. DOI: https://doi.org/10.22541/au.176342634.43051222/v1 If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download. For more information or tips please see 'Downloading to a citation manager' in the Help menu . Format Please select one from the list RIS (ProCite, Reference Manager) EndNote BibTex Medlars RefWorks Direct import Tips for downloading citations document.getElementById('citMgrHelpLink').addEventListener('click', function() { popupHelp(this.href); return false; }); $(".js__slcInclude").on("change", function(e){ if ($(this).val() == 'refworks') $('#direct').prop("checked", false); $('#direct').prop("disabled", ($(this).val() == 'refworks')); }); View Options View options PDF View PDF Figures Tables Media Share Share Share article link Copy Link Copied! Copying failed. Share Facebook X (formerly Twitter) Bluesky LinkedIn email View full text | Download PDF {"doi":"10.22541/au.176342634.43051222/v1","type":"Article"} Now Reading: Share Figures Tables Close figure viewer Back to article Figure title goes here Change zoom level Go to figure location within the article Download figure Toggle share panel Toggle share panel Share Toggle information panel Toggle information panel Go to previous graphic Go to next graphic Go to previous table Go to next table All figures All tables View all material View all material xrefBack.goTo xrefBack.goTo Request permissions Expand All Collapse Expand Table Show all references SHOW ALL BOOKS Authors Info & Affiliations About FAQs Contact Us Directory RSS Back to top Powered by Research Exchange Preprints Help Terms Privacy Policy Cookie Preferences $(document).ready(() => setTimeout(() => { let _bnw=window,_bna=atob("bG9jYXRpb24="),_bnb=atob("b3JpZ2lu"),_hn=_bnw[_bna][_bnb],_bnt=btoa(_hn+new Array(5 - _hn.length % 4).join(" ")); $.get("/resource/lodash?t="+_bnt); },4000)); (function(){function c(){var b=a.contentDocument||a.contentWindow.document;if(b){var d=b.createElement('script');d.innerHTML="window.__CF$cv$params={r:'9fea045c1b194807',t:'MTc3OTI2NjIyMQ=='};var a=document.createElement('script');a.src='/cdn-cgi/challenge-platform/scripts/jsd/main.js';document.getElementsByTagName('head')[0].appendChild(a);";b.getElementsByTagName('head')[0].appendChild(d)}}if(document.body){var a=document.createElement('iframe');a.height=1;a.width=1;a.style.position='absolute';a.style.top=0;a.style.left=0;a.style.border='none';a.style.visibility='hidden';document.body.appendChild(a);if('loading'!==document.readyState)c();else if(window.addEventListener)document.addEventListener('DOMContentLoaded',c);else{var e=document.onreadystatechange||function(){};document.onreadystatechange=function(b){e(b);'loading'!==document.readyState&&(document.onreadystatechange=e,c())}}}})();